© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30082
    Prev
    Next
    INDEX
    Explanations

    largest geographical regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĸ½
    -0.08
    éĥ½åIJĪ
    -0.07
    onge
    -0.07
    åIJĦå¤Ħ
    -0.07
     lắm
    -0.07
    shoot
    -0.07
    verture
    -0.07
    ritis
    -0.07
    æĺ¯ä¸Ģç§į常è§ģçļĦ
    -0.07
    éĤ£æĺ¯æĪij
    -0.07
    POSITIVE LOGITS
    ä¹Łæĺ¯æľĢ
    0.12
    åIJĮæĹ¶ä¹Łæĺ¯
    0.12
    ä¹ĭä¸ĢçļĦ
    0.12
    åĴĮæľĢ
    0.11
    ä¹ĭä¸Ģ
    0.11
    ä¹ĭ称çļĦ
    0.11
    ä¹ĭ称
    0.10
    ä¹Łæĺ¯ä¸ŃåĽ½
    0.09
     ÙĪØ£Ùĥثر
    0.09
    ä¹ĭä¸Ģæĺ¯
    0.09
    Activations Density 0.688%

    No Known Activations